{"id":"https://openalex.org/W4391021782","doi":"https://doi.org/10.1109/asru57964.2023.10389681","title":"SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction","display_name":"SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021782","doi":"https://doi.org/10.1109/asru57964.2023.10389681"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389681","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043390035","display_name":"Kailai Shen","orcid":"https://orcid.org/0000-0002-4786-5832"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailai Shen","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science","Faculty of Electrical Engineering and Computer Science, Ningbo University","Zhejiang Key Laboratory of Mobile Network Application Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Mobile Network Application Technology","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016795475","display_name":"Diqun Yan","orcid":"https://orcid.org/0000-0002-5241-7276"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diqun Yan","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science","Zhejiang Key Laboratory of Mobile Network Application Technology","Faculty of Electrical Engineering and Computer Science, Ningbo University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Mobile Network Application Technology","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100722416","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-7197-1240"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Dong","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science","Faculty of Electrical Engineering and Computer Science, Ningbo University","Zhejiang Key Laboratory of Mobile Network Application Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Mobile Network Application Technology","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103269495","display_name":"Ying Ren","orcid":"https://orcid.org/0000-0002-8019-6239"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Ren","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science","Faculty of Electrical Engineering and Computer Science, Ningbo University","Zhejiang Key Laboratory of Mobile Network Application Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Mobile Network Application Technology","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293970","display_name":"Xiaoxun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxun Wu","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science","Faculty of Electrical Engineering and Computer Science, Ningbo University","Zhejiang Key Laboratory of Mobile Network Application Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Mobile Network Application Technology","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101421878","display_name":"Jing Hu","orcid":"https://orcid.org/0009-0009-6548-5727"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Hu","raw_affiliation_strings":["Ningbo University,Faculty of Electrical Engineering and Computer Science","Faculty of Electrical Engineering and Computer Science, Ningbo University","Zhejiang Key Laboratory of Mobile Network Application Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Faculty of Electrical Engineering and Computer Science, Ningbo University","institution_ids":["https://openalex.org/I109935558"]},{"raw_affiliation_string":"Zhejiang Key Laboratory of Mobile Network Application Technology","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7515395283699036},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6889092326164246},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6631936430931091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4788379967212677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46617865562438965},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.422006756067276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35514235496520996},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1647920310497284},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08930152654647827},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08086588978767395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515395283699036},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6889092326164246},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6631936430931091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4788379967212677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46617865562438965},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.422006756067276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35514235496520996},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1647920310497284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08930152654647827},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08086588978767395},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389681","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1989351718","https://openalex.org/W2592497314","https://openalex.org/W2972394484","https://openalex.org/W3036601975","https://openalex.org/W3161558238","https://openalex.org/W3176511914","https://openalex.org/W3196225973","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W3206996142","https://openalex.org/W3207932315","https://openalex.org/W4223503417","https://openalex.org/W4225672218","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4296069264","https://openalex.org/W4296070386","https://openalex.org/W4297841508","https://openalex.org/W4303633609","https://openalex.org/W4311167834","https://openalex.org/W4323520692","https://openalex.org/W4391021724","https://openalex.org/W6780218876","https://openalex.org/W6803026232","https://openalex.org/W6865530009"],"related_works":["https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2080152487","https://openalex.org/W2239445980","https://openalex.org/W2995553446","https://openalex.org/W2120455979","https://openalex.org/W2151415191","https://openalex.org/W2151664070"],"abstract_inverted_index":{"In":[0,82],"this":[1,46],"paper,":[2],"we":[3,63,105],"propose":[4],"the":[5,25,83,112],"speech":[6],"quality":[7],"assessment":[8],"transformer":[9],"utilizing":[10],"listener":[11],"dependent":[12],"modeling":[13],"(SQAT-LD)":[14],"mean":[15],"opinion":[16],"score":[17],"(MOS)":[18],"prediction":[19,56],"system,":[20],"which":[21],"was":[22],"submitted":[23],"to":[24,45,69,78,110],"2023":[26],"VoiceMOS":[27],"Challenge.":[28],"The":[29],"system":[30,86],"is":[31],"based":[32],"on":[33,49],"a":[34,66],"combination":[35],"of":[36,114],"self-supervised":[37],"learning":[38],"(SSL)":[39],"models":[40],"and":[41,51,72,98],"listener-dependent":[42],"modeling.":[43],"Due":[44],"challenge\u2019s":[47],"emphasis":[48],"real-world":[50],"challenging":[52],"zero-shot":[53],"out-of-domain":[54],"MOS":[55],"in":[57,90,95,101],"three":[58],"different":[59],"voice":[60],"evaluation":[61],"scenarios,":[62],"specifically":[64],"designed":[65],"two-branch":[67],"module":[68],"predict":[70],"scores":[71],"weights":[73],"for":[74],"each":[75],"frame,":[76],"aiming":[77],"achieve":[79],"better":[80],"generalization.":[81],"challenge,":[84],"our":[85,115],"achieved":[87],"fourth":[88],"place":[89,94,100],"Track":[91,96,102],"1a,":[92],"second":[93],"1b":[97],"first":[99],"2.":[103],"Additionally,":[104],"conducted":[106],"an":[107],"ablation":[108],"study":[109],"investigate":[111],"effectiveness":[113],"proposed":[116],"method.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}